基于FFT稀疏压缩感知域内遥感图像融合

Fusion of Remote Sensing Image with Compressive Sensing Based on FFT Spares

压缩感知理论因其远低于乃奎斯特采样率的特性,减少了大量的采样数据。基于这一特性,提出一种在压缩感知域内进行遥感图像融合的方法。该方法首先对图像作快速傅里叶变换(FFT);然后进行测量采样获取压缩感知域数据;再采用权重法对数据进行融合;最后通过重构算法得到融合图像。通过实验得出压缩感知域内遥感图像融合具有数据量少,融合效果好等特点。

Because of its compressive sample feature that the sampling rate is far lower than the Nyquist, a large number of sampled data are reduced by compressive sensing. For this feature, a method of remote sensing image fusion which based on compressive sensing was proposed. Firstly, the image is transformed by fast Fourier. Secondly, Compressive sensing domain data are got by taking measurement samples. Thirdly, the data are fused by taking different weights. Lastly, the fusion image is obtained by reconstruction algorithm. The experimental results proved that the less data needed to be processed and the fusion effect was good by this fusion method.